hamtaa-texttools 1.0.6__tar.gz → 1.0.8__tar.gz

{hamtaa_texttools-1.0.6/hamtaa_texttools.egg-info → hamtaa_texttools-1.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hamtaa-texttools
-Version: 1.0.6
+Version: 1.0.8
 Summary: TextTools is a high-level NLP toolkit built on top of modern LLMs.
 Author-email: Tohidi <the.mohammad.tohidi@gmail.com>, Montazer <montazerh82@gmail.com>, Givechi <mohamad.m.givechi@gmail.com>, MoosaviNejad <erfanmoosavi84@gmail.com>
 License: MIT License
@@ -42,8 +42,6 @@ It provides both **sync (`TheTool`)** and **async (`AsyncTheTool`)** APIs for ma
 
 It provides ready-to-use utilities for **translation, question detection, keyword extraction, categorization, NER extractor, and more** — designed to help you integrate AI-powered text processing into your applications with minimal effort.
 
-**Thread Safety:** All methods in AsyncTheTool are thread-safe, allowing concurrent usage across multiple threads without conflicts.
-
 ---
 
 ## ✨ Features
@@ -78,7 +76,11 @@ Note: This doubles token usage per call because it triggers an additional LLM re
 
 - **`user_prompt="..."`** → Allows you to inject a custom instruction or prompt into the model alongside the main template. This gives you fine-grained control over how the model interprets or modifies the input text.
 
-All these flags can be used individually or together to tailor the behavior of any tool in **TextTools**.
+- **`temperature=0.0`** → Determines how creative the model should respond. Takes a float number from `0.0` to `1.0`.
+
+All these parameters can be used individually or together to tailor the behavior of any tool in **TextTools**.
+
+**Note:** There might be some tools that don't support some of the parameters above.
 
 ---
 
@@ -104,7 +106,6 @@ pip install -U hamtaa-texttools
 
 ```python
 from openai import OpenAI
-from pydantic import BaseModel
 from texttools import TheTool
 
 # Create your OpenAI client
@@ -114,29 +115,19 @@ client = OpenAI(base_url = "your_url", API_KEY = "your_api_key")
 model = "gpt-4o-mini"
 
 # Create an instance of TheTool
-# Note: You can give parameters to TheTool so that you don't need to give them to each tool
-the_tool = TheTool(client=client, model=model, with_analysis=True, output_lang="English")
+the_tool = TheTool(client=client, model=model)
 
 # Example: Question Detection
 detection = the_tool.is_question("Is this project open source?", logprobs=True, top_logprobs=2)
 print(detection["result"])
 print(detection["logprobs"])
-# Output: True
+# Output: True \n --logprobs
 
 # Example: Translation
-# Note: You can overwrite with_analysis if defined at TheTool
-print(the_tool.translate("سلام، حالت چطوره؟", target_language="English", with_analysis=False)["result"])
-# Output: "Hi! How are you?"
-
-# Example: Custom Tool
-# Note: Output model should only contain result key
-# Everything else will be ignored
-class Custom(BaseModel):
-  result: list[list[dict[str, int]]]
-
-custom_prompt = "Something"
-custom_result = the_tool.run_custom(custom_prompt, Custom)
-print(custom_result)
+translation = the_tool.translate("سلام، حالت چطوره؟" target_language="English", with_analysis=True)
+print(translation["result"])
+print(translation["analysis"])
+# Output: "Hi! How are you?" \n --analysis
 ```
 
 ---
@@ -149,7 +140,7 @@ from openai import AsyncOpenAI
 from texttools import AsyncTheTool
 
 async def main():
-    # Create your async OpenAI client
+    # Create your AsyncOpenAI client
     async_client = AsyncOpenAI(base_url="your_url", api_key="your_api_key")
 
     # Specify the model

{hamtaa_texttools-1.0.6 → hamtaa_texttools-1.0.8}/README.md

@@ -8,8 +8,6 @@ It provides both **sync (`TheTool`)** and **async (`AsyncTheTool`)** APIs for ma
 
 It provides ready-to-use utilities for **translation, question detection, keyword extraction, categorization, NER extractor, and more** — designed to help you integrate AI-powered text processing into your applications with minimal effort.
 
-**Thread Safety:** All methods in AsyncTheTool are thread-safe, allowing concurrent usage across multiple threads without conflicts.
-
 ---
 
 ## ✨ Features
@@ -44,7 +42,11 @@ Note: This doubles token usage per call because it triggers an additional LLM re
 
 - **`user_prompt="..."`** → Allows you to inject a custom instruction or prompt into the model alongside the main template. This gives you fine-grained control over how the model interprets or modifies the input text.
 
-All these flags can be used individually or together to tailor the behavior of any tool in **TextTools**.
+- **`temperature=0.0`** → Determines how creative the model should respond. Takes a float number from `0.0` to `1.0`.
+
+All these parameters can be used individually or together to tailor the behavior of any tool in **TextTools**.
+
+**Note:** There might be some tools that don't support some of the parameters above.
 
 ---
 
@@ -70,7 +72,6 @@ pip install -U hamtaa-texttools
 
 ```python
 from openai import OpenAI
-from pydantic import BaseModel
 from texttools import TheTool
 
 # Create your OpenAI client
@@ -80,29 +81,19 @@ client = OpenAI(base_url = "your_url", API_KEY = "your_api_key")
 model = "gpt-4o-mini"
 
 # Create an instance of TheTool
-# Note: You can give parameters to TheTool so that you don't need to give them to each tool
-the_tool = TheTool(client=client, model=model, with_analysis=True, output_lang="English")
+the_tool = TheTool(client=client, model=model)
 
 # Example: Question Detection
 detection = the_tool.is_question("Is this project open source?", logprobs=True, top_logprobs=2)
 print(detection["result"])
 print(detection["logprobs"])
-# Output: True
+# Output: True \n --logprobs
 
 # Example: Translation
-# Note: You can overwrite with_analysis if defined at TheTool
-print(the_tool.translate("سلام، حالت چطوره؟", target_language="English", with_analysis=False)["result"])
-# Output: "Hi! How are you?"
-
-# Example: Custom Tool
-# Note: Output model should only contain result key
-# Everything else will be ignored
-class Custom(BaseModel):
-  result: list[list[dict[str, int]]]
-
-custom_prompt = "Something"
-custom_result = the_tool.run_custom(custom_prompt, Custom)
-print(custom_result)
+translation = the_tool.translate("سلام، حالت چطوره؟" target_language="English", with_analysis=True)
+print(translation["result"])
+print(translation["analysis"])
+# Output: "Hi! How are you?" \n --analysis
 ```
 
 ---
@@ -115,7 +106,7 @@ from openai import AsyncOpenAI
 from texttools import AsyncTheTool
 
 async def main():
-    # Create your async OpenAI client
+    # Create your AsyncOpenAI client
     async_client = AsyncOpenAI(base_url="your_url", api_key="your_api_key")
 
     # Specify the model

{hamtaa_texttools-1.0.6 → hamtaa_texttools-1.0.8/hamtaa_texttools.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hamtaa-texttools
-Version: 1.0.6
+Version: 1.0.8
 Summary: TextTools is a high-level NLP toolkit built on top of modern LLMs.
 Author-email: Tohidi <the.mohammad.tohidi@gmail.com>, Montazer <montazerh82@gmail.com>, Givechi <mohamad.m.givechi@gmail.com>, MoosaviNejad <erfanmoosavi84@gmail.com>
 License: MIT License
@@ -42,8 +42,6 @@ It provides both **sync (`TheTool`)** and **async (`AsyncTheTool`)** APIs for ma
 
 It provides ready-to-use utilities for **translation, question detection, keyword extraction, categorization, NER extractor, and more** — designed to help you integrate AI-powered text processing into your applications with minimal effort.
 
-**Thread Safety:** All methods in AsyncTheTool are thread-safe, allowing concurrent usage across multiple threads without conflicts.
-
 ---
 
 ## ✨ Features
@@ -78,7 +76,11 @@ Note: This doubles token usage per call because it triggers an additional LLM re
 
 - **`user_prompt="..."`** → Allows you to inject a custom instruction or prompt into the model alongside the main template. This gives you fine-grained control over how the model interprets or modifies the input text.
 
-All these flags can be used individually or together to tailor the behavior of any tool in **TextTools**.
+- **`temperature=0.0`** → Determines how creative the model should respond. Takes a float number from `0.0` to `1.0`.
+
+All these parameters can be used individually or together to tailor the behavior of any tool in **TextTools**.
+
+**Note:** There might be some tools that don't support some of the parameters above.
 
 ---
 
@@ -104,7 +106,6 @@ pip install -U hamtaa-texttools
 
 ```python
 from openai import OpenAI
-from pydantic import BaseModel
 from texttools import TheTool
 
 # Create your OpenAI client
@@ -114,29 +115,19 @@ client = OpenAI(base_url = "your_url", API_KEY = "your_api_key")
 model = "gpt-4o-mini"
 
 # Create an instance of TheTool
-# Note: You can give parameters to TheTool so that you don't need to give them to each tool
-the_tool = TheTool(client=client, model=model, with_analysis=True, output_lang="English")
+the_tool = TheTool(client=client, model=model)
 
 # Example: Question Detection
 detection = the_tool.is_question("Is this project open source?", logprobs=True, top_logprobs=2)
 print(detection["result"])
 print(detection["logprobs"])
-# Output: True
+# Output: True \n --logprobs
 
 # Example: Translation
-# Note: You can overwrite with_analysis if defined at TheTool
-print(the_tool.translate("سلام، حالت چطوره؟", target_language="English", with_analysis=False)["result"])
-# Output: "Hi! How are you?"
-
-# Example: Custom Tool
-# Note: Output model should only contain result key
-# Everything else will be ignored
-class Custom(BaseModel):
-  result: list[list[dict[str, int]]]
-
-custom_prompt = "Something"
-custom_result = the_tool.run_custom(custom_prompt, Custom)
-print(custom_result)
+translation = the_tool.translate("سلام، حالت چطوره؟" target_language="English", with_analysis=True)
+print(translation["result"])
+print(translation["analysis"])
+# Output: "Hi! How are you?" \n --analysis
 ```
 
 ---
@@ -149,7 +140,7 @@ from openai import AsyncOpenAI
 from texttools import AsyncTheTool
 
 async def main():
-    # Create your async OpenAI client
+    # Create your AsyncOpenAI client
     async_client = AsyncOpenAI(base_url="your_url", api_key="your_api_key")
 
     # Specify the model

{hamtaa_texttools-1.0.6 → hamtaa_texttools-1.0.8}/hamtaa_texttools.egg-info/SOURCES.txt

@@ -11,24 +11,24 @@ texttools/__init__.py
 texttools/batch/__init__.py
 texttools/batch/batch_manager.py
 texttools/batch/batch_runner.py
-texttools/formatters/base_formatter.py
-texttools/formatters/user_merge_formatter.py
 texttools/prompts/README.md
 texttools/prompts/categorizer.yaml
+texttools/prompts/extract_entities.yaml
+texttools/prompts/extract_keywords.yaml
 texttools/prompts/is_question.yaml
-texttools/prompts/keyword_extractor.yaml
-texttools/prompts/ner_extractor.yaml
-texttools/prompts/question_merger.yaml
-texttools/prompts/rewriter.yaml
+texttools/prompts/merge_questions.yaml
+texttools/prompts/rewrite.yaml
 texttools/prompts/run_custom.yaml
 texttools/prompts/subject_to_question.yaml
-texttools/prompts/summarizer.yaml
+texttools/prompts/summarize.yaml
 texttools/prompts/text_to_question.yaml
-texttools/prompts/translator.yaml
+texttools/prompts/translate.yaml
 texttools/tools/__init__.py
 texttools/tools/async_the_tool.py
 texttools/tools/the_tool.py
 texttools/tools/internals/async_operator.py
+texttools/tools/internals/base_operator.py
+texttools/tools/internals/formatters.py
 texttools/tools/internals/operator.py
 texttools/tools/internals/output_models.py
 texttools/tools/internals/prompt_loader.py

{hamtaa_texttools-1.0.6 → hamtaa_texttools-1.0.8}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hamtaa-texttools"
-version = "1.0.6"
+version = "1.0.8"
 authors = [
   { name = "Tohidi", email = "the.mohammad.tohidi@gmail.com" },
   { name = "Montazer", email = "montazerh82@gmail.com" },

hamtaa_texttools-1.0.8/texttools/tools/async_the_tool.py

@@ -0,0 +1,383 @@
+from typing import Literal, Any
+
+from openai import AsyncOpenAI
+
+from texttools.tools.internals.async_operator import AsyncOperator
+import texttools.tools.internals.output_models as OutputModels
+
+
+class AsyncTheTool:
+    """
+    Async counterpart to TheTool.
+
+    Each method configures the async operator with a specific YAML prompt,
+    output schema, and flags, then delegates execution to `operator.run()`.
+
+    Usage:
+        async_client = AsyncOpenAI(...)
+        tool = TheToolAsync(async_client, model="model-name")
+        result = await tool.categorize("text ...", with_analysis=True)
+    """
+
+    def __init__(
+        self,
+        client: AsyncOpenAI,
+        model: str,
+    ):
+        self.operator = AsyncOperator(client=client, model=model)
+
+    async def categorize(
+        self,
+        text: str,
+        with_analysis: bool = False,
+        user_prompt: str | None = None,
+        temperature: float | None = 0.0,
+        logprobs: bool = False,
+        top_logprobs: int | None = None,
+    ) -> dict[str, str]:
+        """
+        Categorize a text into a single Islamic studies domain category.
+
+        Returns:
+            {"result": <category string>} + ("logprobs" and "analysis" if enabled)
+        """
+        return await self.operator.run(
+            # User parameters
+            text=text,
+            with_analysis=with_analysis,
+            user_prompt=user_prompt,
+            temperature=temperature,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+            # Internal parameters
+            prompt_file="categorizer.yaml",
+            output_model=OutputModels.CategorizerOutput,
+            resp_format="parse",
+            mode=None,
+            output_lang=None,
+        )
+
+    async def extract_keywords(
+        self,
+        text: str,
+        with_analysis: bool = False,
+        output_lang: str | None = None,
+        user_prompt: str | None = None,
+        temperature: float | None = 0.0,
+        logprobs: bool = False,
+        top_logprobs: int | None = None,
+    ) -> dict[str, list[str]]:
+        """
+        Extract salient keywords from text.
+
+        Returns:
+            {"result": [<keyword1>, <keyword2>, ...]} + ("logprobs" and "analysis" if enabled)
+        """
+        return await self.operator.run(
+            # User parameters
+            text=text,
+            with_analysis=with_analysis,
+            output_lang=output_lang,
+            user_prompt=user_prompt,
+            temperature=temperature,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+            # Internal parameters
+            prompt_file="extract_keywords.yaml",
+            output_model=OutputModels.ListStrOutput,
+            resp_format="parse",
+            mode=None,
+        )
+
+    async def extract_entities(
+        self,
+        text: str,
+        with_analysis: bool = False,
+        output_lang: str | None = None,
+        user_prompt: str | None = None,
+        temperature: float | None = 0.0,
+        logprobs: bool = False,
+        top_logprobs: int | None = None,
+    ) -> dict[str, list[dict[str, str]]]:
+        """
+        Perform Named Entity Recognition (NER) over the input text.
+
+        Returns:
+            {"result": [{"text": <entity>, "type": <entity_type>}, ...]} + ("logprobs" and "analysis" if enabled)
+        """
+        return await self.operator.run(
+            # User parameters
+            text=text,
+            with_analysis=with_analysis,
+            output_lang=output_lang,
+            user_prompt=user_prompt,
+            temperature=temperature,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+            # Internal parameters
+            prompt_file="extract_entities.yaml",
+            output_model=OutputModels.ListDictStrStrOutput,
+            resp_format="parse",
+            mode=None,
+        )
+
+    async def is_question(
+        self,
+        text: str,
+        with_analysis: bool = False,
+        user_prompt: str | None = None,
+        temperature: float | None = 0.0,
+        logprobs: bool = False,
+        top_logprobs: int | None = None,
+    ) -> dict[str, bool]:
+        """
+        Detect if the input is phrased as a question.
+
+        Returns:
+            {"result": True} or {"result": False} + ("logprobs" and "analysis" if enabled)
+        """
+        return await self.operator.run(
+            # User parameters
+            text=text,
+            with_analysis=with_analysis,
+            user_prompt=user_prompt,
+            temperature=temperature,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+            # Internal parameters
+            prompt_file="is_question.yaml",
+            output_model=OutputModels.BoolOutput,
+            resp_format="parse",
+            mode=None,
+            output_lang=None,
+        )
+
+    async def text_to_question(
+        self,
+        text: str,
+        with_analysis: bool = False,
+        output_lang: str | None = None,
+        user_prompt: str | None = None,
+        temperature: float | None = 0.0,
+        logprobs: bool = False,
+        top_logprobs: int | None = None,
+    ) -> dict[str, str]:
+        """
+        Generate a single question from the given text.
+
+        Returns:
+            {"result": <generated_question>} + ("logprobs" and "analysis" if enabled)
+        """
+        return await self.operator.run(
+            # User parameters
+            text=text,
+            with_analysis=with_analysis,
+            output_lang=output_lang,
+            user_prompt=user_prompt,
+            temperature=temperature,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+            # Internal parameters
+            prompt_file="text_to_question.yaml",
+            output_model=OutputModels.StrOutput,
+            resp_format="parse",
+            mode=None,
+        )
+
+    async def merge_questions(
+        self,
+        text: list[str],
+        with_analysis: bool = False,
+        output_lang: str | None = None,
+        user_prompt: str | None = None,
+        temperature: float | None = 0.0,
+        logprobs: bool = False,
+        top_logprobs: int | None = None,
+        mode: Literal["default", "reason"] = "default",
+    ) -> dict[str, str]:
+        """
+        Merge multiple questions into a single unified question.
+
+        Returns:
+            {"result": <merged_question>} + ("logprobs" and "analysis" if enabled)
+        """
+        text = ", ".join(text)
+        return await self.operator.run(
+            # User parameters
+            text=text,
+            with_analysis=with_analysis,
+            output_lang=output_lang,
+            user_prompt=user_prompt,
+            temperature=temperature,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+            # Internal parameters
+            prompt_file="merge_questions.yaml",
+            output_model=OutputModels.StrOutput,
+            resp_format="parse",
+            mode=mode,
+        )
+
+    async def rewrite(
+        self,
+        text: str,
+        with_analysis: bool = False,
+        output_lang: str | None = None,
+        user_prompt: str | None = None,
+        temperature: float | None = 0.0,
+        logprobs: bool = False,
+        top_logprobs: int | None = None,
+        mode: Literal["positive", "negative", "hard_negative"] = "positive",
+    ) -> dict[str, str]:
+        """
+        Rewrite a text with different modes.
+
+        Returns:
+            {"result": <rewritten_text>} + ("logprobs" and "analysis" if enabled)
+        """
+        return await self.operator.run(
+            # User parameters
+            text=text,
+            with_analysis=with_analysis,
+            output_lang=output_lang,
+            user_prompt=user_prompt,
+            temperature=temperature,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+            # Internal parameters
+            prompt_file="rewrite.yaml",
+            output_model=OutputModels.StrOutput,
+            resp_format="parse",
+            mode=mode,
+        )
+
+    async def subject_to_question(
+        self,
+        text: str,
+        number_of_questions: int,
+        with_analysis: bool = False,
+        output_lang: str | None = None,
+        user_prompt: str | None = None,
+        temperature: float | None = 0.0,
+        logprobs: bool = False,
+        top_logprobs: int | None = None,
+    ) -> dict[str, list[str]]:
+        """
+        Generate a list of questions about a subject.
+
+        Returns:
+            {"result": [<question1>, <question2>, ...]} + ("logprobs" and "analysis" if enabled)
+        """
+        return await self.operator.run(
+            # User parameters
+            text=text,
+            number_of_questions=number_of_questions,
+            with_analysis=with_analysis,
+            output_lang=output_lang,
+            user_prompt=user_prompt,
+            temperature=temperature,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+            # Internal parameters
+            prompt_file="subject_to_question.yaml",
+            output_model=OutputModels.ReasonListStrOutput,
+            resp_format="parse",
+            mode=None,
+        )
+
+    async def summarize(
+        self,
+        text: str,
+        with_analysis: bool = False,
+        output_lang: str | None = None,
+        user_prompt: str | None = None,
+        temperature: float | None = 0.0,
+        logprobs: bool = False,
+        top_logprobs: int | None = None,
+    ) -> dict[str, str]:
+        """
+        Summarize the given subject text.
+
+        Returns:
+            {"result": <summary>} + ("logprobs" and "analysis" if enabled)
+        """
+        return await self.operator.run(
+            # User parameters
+            text=text,
+            with_analysis=with_analysis,
+            output_lang=output_lang,
+            user_prompt=user_prompt,
+            temperature=temperature,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+            # Internal parameters
+            prompt_file="summarize.yaml",
+            output_model=OutputModels.StrOutput,
+            resp_format="parse",
+            mode=None,
+        )
+
+    async def translate(
+        self,
+        text: str,
+        target_language: str,
+        with_analysis: bool = False,
+        user_prompt: str | None = None,
+        temperature: float | None = 0.0,
+        logprobs: bool = False,
+        top_logprobs: int | None = None,
+    ) -> dict[str, str]:
+        """
+        Translate text between languages.
+
+        Returns:
+            {"result": <translated_text>} + ("logprobs" and "analysis" if enabled)
+        """
+        return await self.operator.run(
+            # User parameters
+            text=text,
+            target_language=target_language,
+            with_analysis=with_analysis,
+            user_prompt=user_prompt,
+            temperature=temperature,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+            # Internal parameters
+            prompt_file="translate.yaml",
+            output_model=OutputModels.StrOutput,
+            resp_format="parse",
+            mode=None,
+            output_lang=None,
+        )
+
+    async def run_custom(
+        self,
+        prompt: str,
+        output_model: Any,
+        output_lang: str | None = None,
+        temperature: float | None = None,
+        logprobs: bool | None = None,
+        top_logprobs: int | None = None,
+    ) -> dict[str, Any]:
+        """
+        Custom tool that can do almost anything!
+
+        Returns:
+            {"result": <Any>}
+        """
+        return await self.operator.run(
+            # User paramaeters
+            text=prompt,
+            output_model=output_model,
+            output_model_str=output_model.model_json_schema(),
+            output_lang=output_lang,
+            temperature=temperature,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+            # Internal parameters
+            prompt_file="run_custom.yaml",
+            resp_format="parse",
+            user_prompt=None,
+            with_analysis=False,
+            mode=None,
+        )